SentenceMIM: A Latent Variable Language Model · HackerPapers discussions

SentenceMIM: A Latent Variable Language Model — HN submission

Thu, 11 Jun 2020 20:57:13 GMT

SentenceMIM: A Latent Variable Language Model

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

SentenceMIM: A Latent Variable Language Model — mentioned by The_rationalist

Sat, 30 May 2020 14:22:56 GMT

Meanwhile, a revolutionary paper that brought for the first successful time a new paradigm to NLP (latent variational autoencoders) and that destroy GPT 3 on text perplexity on the Pen treebank (4.6 vs 20) and with order of magnitudes less parameters is talked about nowhere on the web... https://arxiv.org/abs/2003.02645v2

Paper and discussion history. A mention is not an endorsement.

SentenceMIM: A Latent Variable Language Model — mentioned by The_rationalist

Fri, 29 May 2020 23:14:31 GMT

GPT 3 is obscoleted by order of magnitudes. SMIM has achieved 4.6 of perplexity vs 20 for GPT 3 with and with a thousand less parameters https://arxiv.org/abs/2003.02645 This is the breakthrough of the year and will be silent until the few nerds like me propagate the news to the mainstream

Paper and discussion history. A mention is not an endorsement.

SentenceMIM: A Latent Variable Language Model — mentioned by The_rationalist

Fri, 29 May 2020 23:12:15 GMT

About learning, the ERNIE language model has continuous learning meaning it has not the necessity to fully retrain (I believe) Also GPT 3 is obscoleted by order of magnitudes by SMIM https://arxiv.org/abs/2003.02645

Paper and discussion history. A mention is not an endorsement.